Name
Title | ||
|---|---|---|
Group Sparse Representation With WaveNet Vocoder Adaptation for Spectrum and Prosody Conversion. |
Abstract | ||
|---|---|---|
The statistical approach to voice conversion typically consists of a feature conversion module followed by a vocoder. So far, the feature conversion studies are mainly focused on the conversion of spectrum. However, speaker identity is also characterized by prosodic features, such as fundamental frequency (F0) and energy contour among others. In this paper, we study the transformation of speaker c... |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/TASLP.2019.2910637 | IEEE/ACM Trans. Audio, Speech & Language Processing |
Keywords | Field | DocType |
Phonetics,Sparse matrices,Vocoders,Dictionaries,Continuous wavelet transforms,Training data | Speech corpus,Training set,Prosody,Fundamental frequency,Computer science,Sparse approximation,Speech recognition | Journal |
Volume | Issue | ISSN |
27 | 6 | 2329-9290 |
Citations | PageRank | References |
8 | 0.43 | 9 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Berrak Sisman | 1 | 60 | 10.34 |
| Mingyang Zhang | 2 | 104 | 10.61 |
| Haizhou Li | 3 | 3678 | 334.61 |